Categories Companies Research

Loading the SOTA2 catalog…

Explore

Categories Companies Research

Contribute

Join SOTA2 Contact

SOTA2

© 2026 SOTA2

Build in Bellevue, USA

WizWand is now SOTA2 Research

Papers Benchmarks Datasets Tasks

V-D4RL dataset and benchmarks · SOTA2 Research

Research Datasets

V-D4RL

Benchmarks

Task NameDataset NameSOTA MethodSort

Task NameDataset NameSOTA ResultTrendResults

Visual Offline Reinforcement Learning

V-D4RL (various)

524Cheetah-Run Medium

8

Offline Reinforcement Learning

V-D4RL Walker-walk expert

68.1Normalized Return

5

Offline Reinforcement Learning

V-D4RL Walker-walk medium-expert

93.2Normalized Return

5

Offline Reinforcement Learning

V-D4RL Walker-walk medium

54.8Normalized Return

5

Offline Reinforcement Learning

V-D4RL Walker-walk medium-replay

56.6Normalized Return

5

Offline Reinforcement Learning

V-D4RL Cheetah-run expert

36.6Normalized Return

5

Offline Reinforcement Learning

V-D4RL Cheetah-run medium-expert

73.2Normalized Return

5

Offline Reinforcement Learning

V-D4RL Cheetah-run medium

57.4Normalized Return

5

Offline Reinforcement Learning

V-D4RL Pixel-Based

—Primary metric

0

Popular tasks

Offline Reinforcement Learning Visual Offline Reinforcement Learning

Follow for updates

Join SOTA2 Contact